Run a syntax check on an ABAP package and return syntax errors, warnings, and messages.
Perform syntax check on an ABAP package. Returns syntax errors, warnings, and messages.
| Name | Required | Description | Default |
|---|---|---|---|
| package_name | Yes | Package name. | |
| super_package | No | Optional, and not read by the check endpoint — see CheckPackageLow. Requiring it refused the call before any request was made, for a package with no parent. |
Changes observed during successful MCP inspections.
v16.0.0Input schema / properties / package_name / descriptionPrevious value: -"Package name (e.g., ZMY_PACKAGE)."New value: +"Package name."Input schema / properties / super_package / descriptionPrevious value: -"Super package name (parent package)."New value: +"Optional, and not read by the check endpoint — see CheckPackageLow. Requiring it refused the call before any request was made, for a package with no parent."Input schema / requiredPrevious value: -[
- "package_name",
- "super_package"
-]New value: +[
+ "package_name"
+]v6.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the check is a read-only syntax check and lists return categories, but doesn't disclose whether the check is synchronous, whether it consumes ATC-style resources, whether it has side effects, or whether it depends on activation state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and scope. No waste, though the second sentence is essentially a return-value list which overlaps with output expectations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a check tool with no output schema and no annotations, the description should explain result structure or usage context. It mentions error/warning/message categories but leaves prerequisites, side effects, and differentiation from sibling Check* tools unexplained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the package_name and super_package parameters are already documented in the schema. The description adds no new parameter semantics beyond what's in the schema; baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (syntax check) and resource (ABAP package), and names the return contents (errors, warnings, messages). It distinguishes itself from other Check* siblings by targeting a package specifically, though it doesn't explicitly reference CheckPackageLow or how it differs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this vs. alternatives. The schema's mention of CheckPackageLow hints at a sibling variant (low-level check), but the description itself offers no when-to-use or when-not-to-use context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.